mlsanityData to 7 Oct 2026

Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs

arXiv 2304.11989 ↗First posted 24 Apr 2023cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algorithms struggle to learn policy distributions that are proportional to rewards and have limited exploration capabilities. In this paper, we innovatively formulate the graph active learning problem as a generative process, named GFlowGNN, which generates various samples through sequential actions with probabilities precisely proportional to a predefined reward function. Furthermore, we propose the concept of flow nodes and flow features to efficiently model graphs as flows based on generative flow networks, where the policy network is trained with specially designed rewards. Extensive experiments on real datasets show that the proposed approach has good exploration capability and transferability, outperforming various state-of-the-art methods.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 63 references that are in the map. First posted on arXiv 24 Apr 2023.

Builds on

32 of 63 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  8. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  9. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  10. 2020Towards Deeper Graph Neural Networkscited by 296
  11. 2021GFlowNet Foundationscited by 286
  12. 2019Hyperbolic Graph Neural Networkscited by 244
20 more
  1. 2020Generalization and Representational Limits of Graph Neural Networkscited by 217
  2. 2019Position-aware Graph Neural Networkscited by 203
  3. 2020Design Space for Graph Neural Networkscited by 182
  4. 2022Biological Sequence Design with GFlowNetscited by 172
  5. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  6. 2023A theory of continuous generative flow networkscited by 98
  7. 2021Elastic Graph Neural Networkscited by 67
  8. 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
  9. 2017Active Learning for Graph Embeddingcited by 53
  10. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  11. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  12. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  13. 2021RIM: Reliable Influence-based Active Learning on Graphscited by 23
  14. 2019Exploring Representativeness and Informativeness for Active Learningcited by 21
  15. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  16. 2022Information Gain Propagation: a new way to Graph Active Learning with Soft Labelscited by 16
  17. 2019ActiveHNE: Active Heterogeneous Network Embeddingcited by 11
  18. 2019SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphscited by 11
  19. 2022GFlowCausal: Generative Flow Networks for Causal Discoverycited by 11
  20. 2021Deep Unsupervised Active Learning on Learnable Graphscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023A Theory of Non-Acyclic Generative Flow Networkscited by 12
  2. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  3. 2023GFlowNets with Human Feedbackcited by 3